3RScan
홈페이지 · 논문 44편
A novel dataset and benchmark, which features 1482 RGB-D scans of 478 environments across multiple time steps. Each scene includes several objects whose positions change over time, together with ground truth annotations of object instances and their respective 6DoF mappings among re-scans. Source: [RIO: 3D Object Instance Re-Localization in Changing Indoor Environments](/paper/rio-3d-object-instance-re-localization-in)